EnerJ: approximate data types for safe and general low-power computation

By Adrian Sampson, Werner Dietl, Emily Fortuna, Dan Gnanapragasam, Luis Ceze, D. Grossman. 2011

775 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Chasing Carbon: The Elusive Environmental Footprint of Computing (2020, background): “Recent work has proposed new programming languages to enable more-energy-efﬁcient code [97].”
Minerva: Enabling Low-Power, Highly-Accurate Deep Neural Network Accelerators (2016, methodology): “More recently, with the revival of DNNs, fixed-point bitwidth reduction has been revisited as a method to reduce power and area for resource-constrained computing [47, 48, 13, 49, 21, 17].”
Approximate storage in solid-state memories (2013, methodology): “storage [14, 24, 38], modern non-volatile memory technologies also exhibit properties that make them candidates for storing data approximately.”
Approximate Computing: A Survey (2016, background): “[7] A. Sampson et al., “EnerJ: Approximate data types for safe and general low-power computation,” in Proc.”
A Survey of Techniques for Approximate Computing (2016, methodology): “For example, reducing SRAM supply voltage saves leakage energy but also increases probability of read upset (ﬂipping of a bit during read operation) and write failure (writing a wrong bit) [Sampson et al. 2011].”